==2402== Cachegrind, a cache and branch-prediction profiler
==2402== Copyright (C) 2002-2017, and GNU GPL'd, by Nicholas Nethercote et al.
==2402== Using Valgrind-3.14.0 and LibVEX; rerun with -h for copyright info
==2402== Command: _bin/cxx-opt/osh -n --ast-format none benchmarks/testdata/ltmain.sh
==2402== Parent PID: 2395
==2402== 
--2402-- warning: L3 cache found, using its data for the LL simulation.
==2402== brk segment overflow in thread #1: can't grow to 0x4832000
==2402== (see section Limitations in user manual)
==2402== NOTE: further instances of this message will not be shown
==2402== 
==2402== I   refs:      114,637,279
==2402== I1  misses:      1,115,349
==2402== LLi misses:          8,579
==2402== I1  miss rate:        0.97%
==2402== LLi miss rate:        0.01%
==2402== 
==2402== D   refs:       54,927,268  (28,489,542 rd   + 26,437,726 wr)
==2402== D1  misses:        674,229  (   393,220 rd   +    281,009 wr)
==2402== LLd misses:        157,497  (    14,215 rd   +    143,282 wr)
==2402== D1  miss rate:         1.2% (       1.4%     +        1.1%  )
==2402== LLd miss rate:         0.3% (       0.0%     +        0.5%  )
==2402== 
==2402== LL refs:         1,789,578  ( 1,508,569 rd   +    281,009 wr)
==2402== LL misses:         166,076  (    22,794 rd   +    143,282 wr)
==2402== LL miss rate:          0.1% (       0.0%     +        0.5%  )